sumtyme.ai is an AI research startup focused on modelling the directional changes in time-varying complex systems like financial markets and climate data.
We've developed a new AI architecture called Abstract Generalised Networks (AGNs). These networks are uniquely designed to learn structural abstractions from numerical time series data and model directional movement within time-varying complex systems. AGNs achieve this by leveraging their pre-trained understanding of how information propagates, transforms, and feeds back through a system to generate observable temporal patterns.
AGNs are a unique model architecture because they fundamentally understand how information evolves over time. This enables them to make inferences through dynamic exploration without relying on predefined rules or system-specific training data. As a result, AGNs eliminate the need for post-deployment retraining, making them an ideal foundation for building adaptive, intelligent systems. This offers a significant advantage over traditional neural networks that require extensive training, system-specific feature engineering, and continuous retraining.
Live Demo: Dashboard
Contact us: [email protected]